Video Player is loading.
Current Time 0:00
Duration 0:00
Loaded: 0%
Stream Type LIVE
Remaining Time 0:00
 
1x
    • Chapters
    • descriptions off, selected
    • subtitles off, selected

      Robotic Simulations With Reinforcement Learning at Scale: Harness the Power of NVIDIA Isaac Lab on AWS

      , Sr. Solutions Architect, Amazon
      , Principal IoT Architect, Amazon
      Simulation-based reinforcement learning greatly benefits the field of robotics, enabling models to learn complex tasks quickly. NVIDIA Isaac Lab offers a reinforcement learning environment to train and test robots in realistic simulated environments using physics-based rendering. We'll dive deeper into NVIDIA’s Isaac Lab, AWS Batch, and Amazon EC2 instances powered by NVIDIA GPUs, and highlight the advantages of robotic simulation on AWS. Through hands-on labs, you’ll learn distributed training for robots across multiple GPU nodes, leveraging AWS Batch to accelerate performance. Additionally, we’ll explore the crucial sim-to-real transition, sharing insights and strategies for effectively translating simulation learnings to real-world robotic applications.
      Prerequisite(s):

      None.
      活动: GTC 25
      日期: March 2025
      行业: 所有行业
      NVIDIA 技术: CUDA,Omniverse,Omniverse Replicator,OpenGL,PhysX
      级别: 通用
      话题: 机器人 - 机器人仿真
      语言: 英语
      所在地: